Commits · ea338676b5024188db7f20e54a80b06c8effd72e · change / sglang

"vscode:/vscode.git/clone" did not exist on "704e50f9f02ffd40ba17fc388c71c1a3be06fdde"

23 Sep, 2025 10 commits
- Clean up server args (#10770) · ea338676
  Lianmin Zheng authored Sep 23, 2025
  
  ea338676
- chore: upgrade sgl-kernel 0.3.12 (#10782) · 8c1ef0f9
  Yineng Zhang authored Sep 23, 2025
  
  8c1ef0f9
- Introduce `FutureMap` (#10715) · f5a2faf2
  Liangsheng Yin authored Sep 23, 2025
  
  f5a2faf2
- Move cached kernel to srt.utils (#10776) · 9241f4fd
  Lifu Huang authored Sep 22, 2025
  
  9241f4fd
- Fix trtllm_mla slow concat kernel in MTP (#10777) · 063c3791
  fzyzcjy authored Sep 23, 2025
  
  063c3791
- Use simulate acc len from `sglang.environ` (#10771) · 632b7d8c
  Liangsheng Yin authored Sep 23, 2025
  
  632b7d8c
- [Auto Sync] Update configurer.py (20250923) (#10765) · 113f8f65
  Lianmin Zheng authored Sep 22, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
```
  113f8f65
- [Ascend]optimize Qwen3 on Ascend (#10574) · e22f3a5e
  ronnie_zheng authored Sep 23, 2025
```
Co-authored-by: c30031083 <chenxu140@huawei.com>
```
  e22f3a5e
- [Ascend] optimize Qwen-vl on Ascend (#10556) · 095093ee
  ronnie_zheng authored Sep 23, 2025
```
Co-authored-by: wangqihui01 <wangqh10@163.com>
```
  095093ee
- [Feature] Add MLAProcess for DeepSeek MLA on NPU (#10130) · d27a6f70
  Even Zhou authored Sep 23, 2025
  
  d27a6f70
22 Sep, 2025 16 commits
- [Auto Sync] Update flashattention_backend.py (20250922) (#10762) · 0753ef83
  Yineng Zhang authored Sep 22, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Gordon Gustafson <ggustafson@together.ai>
```
  0753ef83
- fix: kv events with tp > 1 (#10541) · 662393f2
  ishandhanani authored Sep 23, 2025
  
  662393f2
- Enables TRT-LLM backend to be used for target_verify (#10281) · b1bb8e74
  pranavm-nvidia authored Sep 22, 2025
```
Co-authored-by: Pranav Marathe <pranavm@ipp1-3309.ipp1a1.colossus.nvidia.com>
Co-authored-by: fzyzcjy <ch271828n@outlook.com>
```
  b1bb8e74
- Fix multimodal registry and code sync scripts (#10759) · 38c00ed7
  Lianmin Zheng authored Sep 22, 2025
```
Co-authored-by: cctry <shiyang@x.ai>
```
  38c00ed7
- refactor zero copy (#10300) · d4041a5e
  pansicheng authored Sep 23, 2025
```
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
Co-authored-by: huangtingwei <141888744+huangtingwei9988@users.noreply.github.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  d4041a5e
- Fix MTP MoE weight loading with NVFP4 target model. (#10758) · 9c53dad8
  Jue WANG authored Sep 22, 2025
  
  9c53dad8
- Add warnings and remove dependency for deterministic inference (#10724) · aa1c5cf5
  Baizhou Zhang authored Sep 22, 2025
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  aa1c5cf5
- Fix CI TestChunkedSGMV (#10737) · 2101d93b
  Lifu Huang authored Sep 22, 2025
  
  2101d93b
- fix capture_bs when speculative decoding enabled (#10730) · 944f1ea0
  feng397 authored Sep 22, 2025
  
  944f1ea0
- EPLB: prefer to use physical experts in the same node (#9849) · 9d7e82a0
  Yingchun Lai authored Sep 22, 2025
  
  9d7e82a0
- Convert FLASHINFER_WORKSPACE_SIZE to integer (#10731) · f0580551
  Yang Yu authored Sep 22, 2025
  
  f0580551
- [4/4] Introduce CachedKernel to reduce CSGMV kernel launch overheads by 60% (#10709) · 635ccda6
  Lifu Huang authored Sep 21, 2025
  
  635ccda6
- [2/2] Support deterministic inference for temperature > 0 (#10678) · e2ac7888
  Qiaolin Yu authored Sep 21, 2025
```
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
```
  e2ac7888
- [deterministic inference] Move batch invariant pkg to sglang (#10695) · 86527a47
  Stefan He authored Sep 21, 2025
  
  86527a47
- Support deterministic inference with triton backend (#10694) · 134b4f7e
  Ethan (Yusheng) Su authored Sep 21, 2025
  
  134b4f7e
- [Auto Sync] Update deepseek_v2.py (20250922) (#10717) · f67d1f45
  Yineng Zhang authored Sep 21, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Michael Granado <mgranado@together.ai>
```
  f67d1f45
21 Sep, 2025 5 commits
- Refactors radix cache for extra key support (#10317) · 12d6cf18
  Xinyuan Tong authored Sep 21, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  12d6cf18
- [3/4] Speed up CSGMV backend perf by 10% through dynamic chunking + kernel optimization (#10592) · 08ecd0aa
  Lifu Huang authored Sep 20, 2025
  
  08ecd0aa
- Super tiny fix extra logs (#10697) · 720c1c8c
  fzyzcjy authored Sep 21, 2025
  
  720c1c8c
- feat: update server args (#10696) · d403c143
  Yineng Zhang authored Sep 20, 2025
```
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  d403c143
- [Feature] Support deterministic inference with FA3 backend (#10651) · cba0d8c3
  Stefan He authored Sep 20, 2025
  
  cba0d8c3
20 Sep, 2025 8 commits
- [Auto Sync] Update modelopt_quant.py (20250920) (#10688) · f1d78923
  Yineng Zhang authored Sep 20, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
```
  f1d78923
- fix: remove awq_dequantize deps (#10686) · 7c876de7
  Yineng Zhang authored Sep 20, 2025
  
  7c876de7
- fix(disagg): fix sending KV cache in case of MLA for NIXL backend (#10673) · 2b7417bf
  dmitrygx authored Sep 20, 2025
  
  2b7417bf
- Replace os.environ in layernorm.py (#10684) · f1116495
  Baizhou Zhang authored Sep 20, 2025
  
  f1116495
- [Performance] Qwen3-Next: optimize causal_conv1d_fn triton kernel - up to 9% faster (#10680) · bd7eb020
  Binyao Jiang authored Sep 20, 2025
  
  bd7eb020
- [Auto Sync] Update deepseek_v2.py (20250920) (#10683) · b17e67df
  Yineng Zhang authored Sep 19, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
```
  b17e67df
- [1/2] Support deterministic inference with flashinfer attention backend (#10645) · 8ecef73f
  Baizhou Zhang authored Sep 19, 2025
```
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
```
  8ecef73f
- [Auto Sync] Update model_runner.py (20250920) (#10679) · 60e2a7ce
  Yineng Zhang authored Sep 19, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
```
  60e2a7ce
19 Sep, 2025 1 commit
- limit sgl-kernel causal conv1d to cuda only (#10648) · d88ef4a3
  Jinyan Chen authored Sep 20, 2025
```
Co-authored-by: Jinyan Chen <jinyanc@nvidia.com>
```
  d88ef4a3